Bojun Zhang

Junhong Liang, Bojun Zhang

Spelling correction from visual input poses unique challenges for vision language models (VLMs), as it requires not only detecting but also correcting textual errors directly within images. We present ReViCo (Real Visual Correction), the first benchmark that systematically evaluates VLMs on real-world visual spelling correction across Chinese and English. ReViCo contains naturally occurring errors collected from real-world image data and supports fine-grained evaluation at both image and token levels. Through comprehensive experiments on representative cascaded (Qwen) and native (InternVL) open-source models, as well as closed-source systems (GPT-4o, Claude), we show that current VLMs fall significantly short of human performance, particularly in correction. To address these limitations, we explore two solution paradigms: a Joint OCR-Correction pipeline and a Background Information enhanced approach, both of which yield consistent performance gains. Our analysis highlights fundamental limitations of existing architectures and provides actionable insights for advancing multimodal spelling correction.

Bojun Zhang, Huiyu Yang, Yunpeng Wang et al.

Rapid aerodynamic evaluation is crucial for modern vehicle design, yet existing neural operators struggle to capture intricate spatial correlations. We propose the rotary-enhanced transformer operator (RETO), a novel neural solver featuring a dual-stage spatial awareness mechanism: sinusoidal-cosine encodings for global referencing and rotary positional encodings (RoPE) for relative displacements. RoPE encodes spatial relations via unitary rotations, enforcing translation invariance and enhancing local gradient resolution. RETO is validated on ShapeNet and the high-fidelity DrivAerML benchmark. On ShapeNet, RETO achieves a relative $L_2$ error of 0.063, outperforming RegDGCNN at 0.125 and representing a 16\% improvement over the Transolver baseline, which yields an error of 0.075. These performance gains are further amplified on the DrivAerML dataset, where RETO achieves relative $L_2$ errors of 0.089 for surface pressure and 0.097 for velocity. In comparison, Transolver results in errors of 0.116 and 0.121 for the same metrics, indicating that RETO achieves precision enhancements of 23\% and 19\%, respectively. For comprehensive comparison, the surface pressure and velocity errors for AB-UBT are 0.102 and 0.124, while RegDGCNN yields 0.235 and 0.312, respectively. Information-theoretical analysis shows that the entropy peak of RETO at 0.35 is significantly lower than that of Transolver at 0.75 under $10^4$ resolution, indicating a focused attentional mechanism capable of preserving localized gradients against global diffusion.

Junhong Liang, Bojun Zhang

Existing Chinese ASR correction methods have not effectively utilized Pinyin information, a unique feature of the Chinese language. In this study, we address this gap by proposing a \textbf{P}inyin \textbf{E}nhanced \textbf{R}ephrasing \textbf{L}anguage model (PERL) pipeline, designed explicitly for N-best correction scenarios. We conduct experiments on the Aishell-1 dataset and our newly proposed DoAD dataset. The results show that our approach outperforms baseline methods, achieving a 29.11\% reduction in Character Error Rate on Aishell-1 and around 70\% CER reduction on domain-specific datasets. PERL predicts the correct length of the output, leveraging the Pinyin information, which is embedded with a semantic model to perform phonetically similar corrections. Extensive experiments demonstrate the effectiveness of correcting wrong characters using N-best output and the low latency of our model.

Bojun Zhang, Hangjian Ye, Hao Zheng et al.

Fine-grained 3D part segmentation is crucial for enabling embodied AI systems to perform complex manipulation tasks, such as interacting with specific functional components of an object. However, existing interactive segmentation methods are largely confined to coarse, instance-level targets, while non-interactive approaches struggle with sparse, real-world scans and suffer from a severe lack of annotated data. To address these limitations, we introduce PinPoint3D, a novel interactive framework for fine-grained, multi-granularity 3D segmentation, capable of generating precise part-level masks from only a few user point clicks. A key component of our work is a new 3D data synthesis pipeline that we developed to create a large-scale, scene-level dataset with dense part annotations, overcoming a critical bottleneck that has hindered progress in this field. Through comprehensive experiments and user studies, we demonstrate that our method significantly outperforms existing approaches, achieving an average IoU of around 55.8% on each object part under first-click settings and surpassing 71.3% IoU with only a few additional clicks. Compared to current state-of-the-art baselines, PinPoint3D yields up to a 16% improvement in IoU and precision, highlighting its effectiveness on challenging, sparse point clouds with high efficiency. Our work represents a significant step towards more nuanced and precise machine perception and interaction in complex 3D environments.